Research Explorer

Your browser does not support JavaScript or JavaScript is not enabled. Without JavaScript some functions of this webapplication may be disabled or cause error messages. To enable JavaScript, please consult the manual of your browser or contact your system administrator.

Project

A data-driven approach to constructing domain-specific and implicit sentiment knowledge bases

Outputs and Outcomes

Code

3E006116

Duration

01 October 2016 → 31 January 2019

Funding

Research Foundation - Flanders (FWO)

Promotor

Veronique Hoste

Fellow

Bart Desmet

Research disciplines

Humanities and the arts
- Computational linguistics

Keywords

lexicons sentiment analysis computational linguistics Language technology

Project description

Polarity lexicons, an important resource for automatic sentiment analysis in text, are expensive to build manually, and they ignore the complexity of how sentiment can be expressed (e.g. implicitly, using factual statements that entail a sentiment). This project investigates a method for automatically deriving polarity lexicons from large corpora, allowing more complex representations than single lemmas.

English

Dutch

English

Cookie settings

In addition to functional cookies which are necessary for the website to function, Ghent University uses non-functional cookies such as statistical cookies and social media cookies. These non-functional cookies can also be placed by third parties, for example to measure the use of the site or to share content on social media. Certain media are only available if you accept the cookies. You can set and modify your cookie preferences yourself. Find out what cookies we use and why in the Cookie Statement.

Analytics

AnalyticsWe'll collect information about your visit to our site. It helps us understand how the site is used – what's working, what might be broken and what we should improve.

Powered by